Kaj Bostrom
8 papers · 2020–2024 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (22) 🐣 Hot Topic Early Bird 🔥 Unstoppable · Bronze
📈
Trend Setter
Top co-authors
Research topics
Natural Language Processing
(7)
Machine Learning
(5)
Applications
(5)
Artificial Intelligence
(4)
Core AI
(4)
Generation
(4)
Deep Learning
(3)
Knowledge & Reasoning
(2)
Core Methods
(2)
Learning Types · Machine Learning
(2)
Optimization & Theory
(2)
Reasoning
(2)
Understanding
(2)
Architectures
(1)
Learning Types · Deep Learning
(1)
Keywords
deductive reasoning
(4)
natural language inference
(3)
natural language deduction
(2)
text generation
(2)
question answering
(1)
synthetic data generation
(1)
logical reasoning
(1)
code generation
(1)
in-context learning
(1)
explanation generation
(1)
program synthesis
(1)
natural language understanding
(1)
semantic analysis
(1)
natural language
(1)
benchmark dataset
(1)
semantic embedding
(1)
language model
(1)
model fine-tuning
(1)
subword tokenization
(1)
semantic parsing
(1)
Papers
Language-to-Code Translation with a Single Labeled Example
EMNLP 2024
MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning
ICLR 2024
Deductive Additivity for Planning of Natural Language Proofs
ACL 2023
Lil-Bevo: Explorations of Strategies for Training Language Models in More Humanlike Ways
CoNLL 2023
Natural Language Deduction through Search over Statement Compositions
EMNLP 2022
Natural Language Deduction with Incomplete Information
EMNLP 2022
Flexible Generation of Natural Language Deductions
EMNLP 2021
Byte Pair Encoding is Suboptimal for Language Model Pretraining
EMNLP 2020